NVIDIA AI Blueprint for Video Search and Summarization (VSS) is a reference architecture for applications that use AI to search, analyze, question, and summarize live or recorded video. It is intended for building video analytics agents with vision-language models, language models, retrieval-augmented generation, and NVIDIA NIM microservices. The catalogue entries provide coding-agent rules, skills, commands, agents, instructions, and settings associated with the project.
Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add NVIDIA-AI-Blueprints/video-search-and-summarization --skill vss-manage-video-io-storagegit clone --depth 1 https://github.com/NVIDIA-AI-Blueprints/video-search-and-summarizationWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/nvidia-ai-blueprints/video-search-and-summarization/vss-manage-video-io-storage)<a href="https://agentmods.dev/skills/nvidia-ai-blueprints/video-search-and-summarization/vss-manage-video-io-storage"><img src="https://agentmods.dev/badge/skills/nvidia-ai-blueprints/video-search-and-summarization/vss-manage-video-io-storage/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/nvidia-ai-blueprints/video-search-and-summarization/vss-manage-video-io-storage"><img src="https://agentmods.dev/badge/skills/nvidia-ai-blueprints/video-search-and-summarization/vss-manage-video-io-storage.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Tool Misuse · line 258 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00143 | $0.06661 |
| Opus 5.5 | $0.00057 | $0.02664 |
| Sonnet 5.5 | $0.00029 | $0.01332 |
| Haiku 4.5 | $0.00014 | $0.00666 |
Grade A, and why
vss-manage-video-io-storage scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 18d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- `curl` only for the direct-REST cases in **Instructions**, and `jq` for reading JSON. Use `set -o pipefail`, or capture stdout before piping. Docker is needed only for Compose deployment diagnostics. How it starts
The opening of the file, as written. The whole thing — 286 lines — stays where its author put it; the contents beside it link to each section on GitHub.
VIOS Operations
Purpose
Manage VIOS video input/output and storage with vss vios: sensors, streams,
uploads, snapshots, clip URLs, and timelines. NvStreamer stays a
separate REST API, used only for an explicit synthetic RTSP request.
When to Use
- Drive
vss vios— add or delete a video file or RTSP stream, list sensors, show configured sensors, get a snapshot or clip URL (media_url), or upload a video file - Serve test/sample videos as synthetic RTSP via NvStreamer, or drive the NvStreamer →
vss vios add --type streamhandoff - Provision a source into a configured deployment so its notification receivers fan it out to RT-CV / RT-Embed / RT-VLM
Not for VLM inference or ad-hoc visual Q&A (vss-ask-video), semantic search (vss-search-archive), narrative summaries (vss-summarize-video), or reading analytics/incidents (vss-query-analytics).
Prerequisites
- The
vssCLI onPATH. The OpenClaw and Hermes harness images ship it; anywhere else, install it from the same checkout as this skill so the CLI and the skill match:uv tool install <checkout>/libs/vss/cli. - A deployment already recorded by
vss configure. Confirm withvss configure show.vss configure --base-urlis the only place an endpoint is supplied, and only the ingress origin the operator already has (VSS_PUBLIC_URL). If nothing is recorded andVSS_PUBLIC_URLis unset, stop and ask for the ingress origin. Never default a host or port. Exit codes, empty results, and pipe rules live in the repository rootAGENTS.md. - NGC credentials in
$NGC_CLI_API_KEYand$NVIDIA_API_KEYfor any image pulls. curlonly for the direct-REST cases in Instructions, andjqfor reading JSON. Useset -o pipefail, or capture stdout before piping. Docker is needed only for Compose deployment diagnostics.
Instructions
Use vss vios for list, add, delete, timeline, clip, and snapshot. Address media by sensor name. Do not build a sensorId from a name. --type (video for a file-backed sensor, stream for RTSP) is required on delete, a filter on list, and an optional check on add, which reads the kind from SOURCE (rtsp:// or rtsps:// is a stream, anything else a video). Do not hand-build a clip window when vss vios clip --sensor NAME can resolve it. Do not navigate the UI.
What ships with it
9 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- evals/evals.json 3.0 KB
- evals/nvstreamer_ops.json 34 KB
- evals/vios_ops.json 32 KB
- references/api-reference.md 57 KB
- references/deploy-vios-service.md 37 KB
- references/integrate-vios-service.md 56 KB
- references/nvstreamer-api-reference.md 24 KB
- references/provision-vios-source.md 25 KB
- skill-card.md 3.9 KB
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 18d ago Changed · -2 lines · -6 tokens per session f77f83c30fdc
- 22d ago Changed · -55 lines · +64 tokens per session 0bc627da613b
- 28d ago Changed a29d79982660
- 29d ago Changed · +8 lines 94cf049b044e
- 1mo ago Changed · +1 lines 8a18a9712b32
- 1mo ago Changed · +7 lines · +3 tokens per session 3a73766262cd
- 1mo ago Changed · +5 lines b95ce5c7d31c
- 1mo ago Changed a3cbf72e30f1
- 1mo ago Changed · +21 lines 48c02ef9b836
- 1mo ago First seen · 301 lines · 82 tokens per session scan A 6433a3bbcbec
vss-manage-video-io-storage is a skill published in the GitHub repository NVIDIA-AI-Blueprints/video-search-and-summarization (1,953 stars, last pushed today), licensed Apache-2.0. It adds 143 tokens to every session and 6,661 once invoked, about $0.0006 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
langchain4j-spring-boot-integration
Provides integration patterns for LangChain4j with Spring Boot. Configures AI model beans, sets up chat memory with Spring context, integrates RAG pipelines with Spring Data, and handles auto-configuration, dependency injection, and Spring ecosystem integration. Use when embedding LangChain4j into Spring Boot…
azure-cognitive-search
Expert knowledge for Azure AI Search development including troubleshooting, best practices, decision making, architecture & design patterns, limits & quotas, security, configuration, integrations & coding patterns, and deployment. Use when configuring data sources, skillsets, vector/semantic search, indexers, or…
advogado-criminal
Assistente de pesquisa informativa, sem credenciais profissionais, sobre em Maria da Penha, violencia domestica, feminicidio, direito penal brasileiro, medidas protetivas, inquerito policial e acao pe.
ai-product
Every product will be AI-powered. The question is whether you'll build it right or ship a demo that falls apart in production. This skill covers LLM integration patterns, RAG architecture, prompt engineering that scales, AI UX that users trust, and cost optimization that doesn't bankrupt you. Use when: keywords…
data-manager-api-setup
Guides developers through client library installation and authentication setup steps for the Data Manager API. Use this skill when a user is getting started with the Data Manager API and needs to setup their local environment, install the client library, or setup access to the API. Don't use for implementing audience…
mem0-test-integration
Verify a Mem0 integration produced by /mem0-integrate. Runs in the same workspace on the same branch (loose coupling) — installs dependencies, runs the repo's native test suite, then exercises a real end-to-end smoke flow against the user's API key. Produces a scorecard. TRIGGER when: user has just run /mem0-integrate…